Papers
6
Total Citations
254
H-Index
4
About
Liwei Cao is a pioneering researcher at the intersection of machine learning, automated experimentation, and chemical product design. Their work spans two interconnected domains: asymmetric catalysis optimization and formulation development, united by a shared commitment to using artificial intelligence to accelerate complex chemical discovery. Cao's most celebrated contribution, published in 2019 and amassing 139 citations, demonstrated that machine learning combined with molecular descriptors could rationally guide solvent selection in asymmetric catalysis. By training a multi-objective algorithm on just 25 solvents, their team achieved superior conversion rates and diastereomeric excess in Josiphos-catalyzed hydrogenation reactions — a landmark proof-of-concept for data-driven catalysis. This work helped establish that small, strategically chosen datasets could unlock powerful predictive models. Equally impactful is Cao's sustained effort to modernize formulation science. Their 2021 study coupling Thompson sampling with robotic experimentation (76 citations) showed how AI-driven design-of-experiments could meaningfully compress time-to-market for complex multi-ingredient products. Subsequent papers have extended these methods to ingredient selection and sustainable reformulation challenges. Across their portfolio, Cao exemplifies the growing paradigm of closed-loop, robot-assisted chemical research, offering students and practitioners a compelling template for integrating automation with intelligent experimental design.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Automated robotic platforms in design and development of formulations23 citations · 2021
- 4
- 5Machine Learning-aided Process Design for Formulated Products4 citations · 2020
- 6